US11925481B2 - Information processing device, information processing method, and program - Google Patents

Information processing device, information processing method, and program Download PDF

Info

Publication number
US11925481B2
US11925481B2 US17/241,077 US202117241077A US11925481B2 US 11925481 B2 US11925481 B2 US 11925481B2 US 202117241077 A US202117241077 A US 202117241077A US 11925481 B2 US11925481 B2 US 11925481B2
Authority
US
United States
Prior art keywords
subject
group
information representing
physique
medical image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US17/241,077
Other languages
English (en)
Other versions
US20210248742A1 (en
Inventor
Kenta Yamada
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujifilm Corp
Original Assignee
Fujifilm Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujifilm Corp filed Critical Fujifilm Corp
Assigned to FUJIFILM CORPORATION reassignment FUJIFILM CORPORATION ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: YAMADA, KENTA
Publication of US20210248742A1 publication Critical patent/US20210248742A1/en
Application granted granted Critical
Publication of US11925481B2 publication Critical patent/US11925481B2/en
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/45—For evaluating or diagnosing the musculoskeletal system or teeth
    • A61B5/4504—Bones
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271—Specific aspects of physiological measurement analysis
    • A61B5/7278—Artificial waveform generation or derivation, e.g. synthesising signals from measured signals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/7475—User input or interface means, e.g. keyboard, pointing device, joystick
    • A61B5/748—Selection of a region of interest, e.g. using a graphics tablet
    • A61B5/7485—Automatic selection of region of interest
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/2431—Multiple classes
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2503/00—Evaluating a particular growth phase or type of persons or animals
    • A61B2503/06—Children, e.g. for attention deficit diagnosis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2576/00—Medical imaging apparatus involving image processing or analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0073—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence by tomography, i.e. reconstruction of 3D images from 2D projections
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/05—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves 
    • A61B5/055—Detecting, measuring or recording for diagnosis by means of electric currents or magnetic fields; Measuring using microwaves or radio waves  involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
    • A61B5/1077—Measuring of profiles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/48—Other medical applications
    • A61B5/4887—Locating particular structures in or on the body
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30008—Bone
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/03—Recognition of patterns in medical or anatomical images
    • G06V2201/033—Recognition of patterns in medical or anatomical images of skeletal patterns

Definitions

  • the present disclosure relates to an information processing device, an information processing method, and a program.
  • a face detection method of detecting a face included in an input image while changing an inclination of a face to be detected is disclosed (refer to JP2007-128127A).
  • face detection is performed by any detection processing of first detection processing or second detection processing according to the inclination of the face to be detected.
  • An image processing device that detects a face from an input image using a face detection method according to a type of the input image is disclosed (refer to JP2009-070099A).
  • the information processing device of the present disclosure comprises an extraction unit that extracts information representing a physique of a subject from an image obtained by imaging the subject, a specification unit that specifies a group in which the subject is classified, using the information representing the physique of the subject extracted by the extraction unit, an input unit that inputs image data representing a medical image obtained by imaging the subject to a learned model corresponding to the group specified by the specification unit among learned models obtained in advance for each group by machine learning using learning data for each group, and an acquisition unit that acquires information representing an area extracted from the medical image, which is output from the learned model with the input by the input unit.
  • FIG. 1 is a block diagram showing an example of a configuration of a diagnosis support system according to an embodiment.
  • FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing device according to the embodiment.
  • FIG. 3 is a diagram showing an example of a learned model according to the embodiment.
  • FIG. 4 is a block diagram showing an example of a functional configuration of the information processing device according to the embodiment.
  • FIG. 5 is a flowchart showing an example of diagnosis support processing according to the embodiment.
  • the diagnosis support system 10 includes an image management device 12 and an information processing device 14 .
  • the image management device 12 and the information processing device 14 are each connected to a network N, and communication therebetween is possible through the network N.
  • the image management device 12 stores image data (hereinafter referred to as “medical image data”) representing a medical image obtained by imaging a subject via an imaging device that images a medical image such as computed tomography (CT) or magnetic resonance imaging (MRI). Examples of the image management device 12 include a picture archiving and communication system (PACS) and the like.
  • the information processing device 14 supports the diagnosis using the medical image data stored in the image management device 12 . Examples of the information processing device 14 include information processing devices such as a personal computer and a server computer.
  • the information processing device 14 includes a central processing unit (CPU) 20 , a memory 21 as a temporary storage area, and a nonvolatile storage unit 22 .
  • the information processing device 14 includes a display unit 23 such as a liquid crystal display, an input unit 24 such as a keyboard or a mouse, and a network interface (I/F) 25 connected to the network N.
  • the CPU 20 , the memory 21 , the storage unit 22 , the display unit 23 , the input unit 24 , and the network I/F 25 are connected to a bus 26 .
  • the storage unit 22 may be a non-transitory recording medium such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory.
  • the storage unit 22 stores an information processing program 30 .
  • the CPU 20 reads the information processing program 30 from the storage unit 22 , develops the program in the memory 21 , and loads and executes the developed information processing program 30 .
  • a plurality of learned models 32 are stored in the storage unit 22 .
  • the learned model 32 will be described with reference to FIG. 3 .
  • a form in which a neural network including an input layer, a plurality of interlayers, and an output layer is applied will be described as an example of the learned model 32 in the present embodiment.
  • the learned model 32 is stored in the storage unit 22 for each group in which the subject is classified.
  • the storage unit 22 stores the learned model 32 corresponding to a group of children and the learned model 32 corresponding to a group of adults, which are classified by the age of the subject.
  • the child as used herein means a child younger than a predetermined age
  • the adult means a person equal to or older than the predetermined age.
  • a boundary age between the child and the adult is not particularly limited and may be, for example, 15 years old or 18 years old.
  • the number of groups in which subjects are classified is not limited to two and may be three or more.
  • the medical image data obtained by imaging the subject via CT is input to the learned model 32 .
  • output data information representing an area extracted from the medical image indicated by the input medical image data is output from the learned model 32 .
  • the learned model 32 extracts a lung area in the medical image indicated by the input medical image data and outputs image data representing an image in which the extracted lung area is filled with a predetermined color (for example, red).
  • a predetermined color for example, red
  • the extracted lung area is shown as a shaded area.
  • the learned model 32 may extract any one of the left and right lung areas, an area other than the lungs, or a plurality of types of areas.
  • Examples of the areas extracted by the learned model 32 include various organ areas, bone areas, blood vessel areas, and subcutaneous fat areas.
  • the learned model 32 is a model obtained in advance by performing machine learning for each group described above with a plurality of sets of medical image data and information representing the lung area in the medical image data as learning data (also referred to as teacher data). That is, the learned model 32 corresponding to the group of children is a model obtained in advance by performing the machine learning using the medical image data obtained by imaging the subject classified as a child and the information representing the lung area in the medical image data as the learning data.
  • the learned model 32 corresponding to the group of adults is a model obtained in advance by performing the machine learning using the medical image data obtained by imaging the subject classified as an adult and the information representing the lung area in the medical image data as the learning data.
  • an example of a method used for the machine learning includes an error backpropagation method or the like.
  • To obtain in advance means to obtain a model before selecting a selected model corresponding to the model and the specified group.
  • the learning using the learning data of each group can be performed by this information processing device, or can be performed by an external device by sending the group information specified by this information processing device to the external device.
  • the external device may acquire the physique information and classify into the groups before learning, and the information processing device may acquire or save the model learned by the external device.
  • the information processing device 14 includes an extraction unit 40 , a specification unit 42 , an input unit 44 , an acquisition unit 46 , and an output unit 48 .
  • the CPU 20 executes the information processing program 30 to function as the extraction unit 40 , the specification unit 42 , the input unit 44 , the acquisition unit 46 , and the output unit 48 .
  • the extraction unit 40 extracts information representing a physique of the subject from the medical image indicated by the medical image data acquired from the image management device 12 by the input unit 44 described below.
  • the extraction unit 40 performs image analysis processing on the medical image to extract a skeleton of the subject as the information representing the physique of the subject.
  • the bone area has a higher signal value in a CT image than other areas. Therefore, the extraction unit 40 extracts an area with a signal value that is equal to or higher than a threshold value from the medical image to extract the skeleton of the subject.
  • the extraction unit 40 identifies the characteristics of the vertebrae and the pelvis in the extracted skeleton and identifies parts such as the head, chest, abdomen, and lower limbs.
  • the specification unit 42 specifies the group in which the subject is classified, using the information representing the physique of the subject extracted by the extraction unit 40 .
  • the specification unit 42 specifies whether the group in which the subject is classified are children or adults, using the skeleton of the subject extracted by the extraction unit 40 .
  • the specification unit 42 specifies whether the group in which the subject is classified is children or adults from a proportion of the head in the whole body of the skeleton of the subject.
  • the proportion of the head in the whole body is about 15% to 25% for infants to elementary school students and is less than 15% for high school students or older. Therefore, it is possible to specify the group in which the subject is classified, with 15% as the threshold value, for example.
  • the input unit 44 acquires the medical image data from the image management device 12 and inputs the acquired medical image data to the learned model 32 corresponding to the group specified by the specification unit 42 among the learned models 32 stored in the storage unit 22 .
  • the acquisition unit 46 acquires the information representing the area extracted from the medical image output from the learned model 32 in response to the input by the input unit 44 .
  • the output unit 48 outputs the information representing the area extracted from the medical image acquired by the acquisition unit 46 to the display unit 23 .
  • This output for example, an image in which the lung area is filled with a predetermined color is displayed on the display unit 23 .
  • a user diagnoses the subject using the image displayed on the display unit 23 .
  • the output unit 48 may output (store) the information representing the area extracted from the medical image acquired by the acquisition unit 46 to the storage unit 22 or output (transmit) the information to the image management device 12 .
  • the CPU 20 executes the information processing program 30 to execute diagnosis support processing shown in FIG. 5 .
  • the diagnosis support processing shown in FIG. 5 is executed, for example, in a case where an instruction to execute the diagnosis support processing is input by the user through the input unit 24 .
  • step S 10 in FIG. 5 the input unit 44 acquires the medical image data from the image management device 12 .
  • step S 12 the extraction unit 40 extracts the information representing the physique of the subject from the medical image indicated by the medical image data acquired by the processing of step S 10 , as described above.
  • step S 14 the specification unit 42 specifies the group in which the subject is classified, using the information representing the physique of the subject extracted by the processing of step S 12 , as described above.
  • step S 16 the input unit 44 inputs the medical image data acquired in step S 10 to the learned model 32 corresponding to the group specified by the processing of step S 14 among the learned models 32 stored in the storage unit 22 .
  • step S 18 the acquisition unit 46 acquires information representing the area extracted from the medical image output from the learned model 32 in response to the input by the processing of step S 16 .
  • step S 20 the output unit 48 outputs the information representing the area extracted from the medical image acquired by the processing of step S 18 to the display unit 23 , as described above. In a case where the processing of step S 20 ends, the diagnosis support processing ends.
  • the group in which the subject is classified is specified by using the information representing the physique of the subject, and the image data representing the medical image obtained by imaging the subject is input to the learned model 32 corresponding to the specified group.
  • the information representing the area extracted from the medical image output from the learned model 32 is acquired.
  • the medical image obtained by imaging the subject differs in an amount of radiation at the time of imaging, a size of an organ, an amount of fat, and the like, depending on whether the subject is a child or an adult.
  • the child is characterized by a smaller amount of radiation at the time of imaging, a smaller organ, and a smaller amount of fat than the adult. Therefore, it is possible to accurately extract the target area from the medical image by properly using the learned model 32 corresponding to the child and the learned model 32 corresponding to the adult as in the present embodiment.
  • the information representing the physique of the subject is extracted from the medical image obtained by imaging the subject, and the group in which the subject is classified is specified by using the extracted information. Therefore, a dedicated image for extracting the physique of the subject is not required, and the user can specify the group without setting the group. As a result, it is possible to efficiently specify the group in which the subject is classified.
  • a form may be employed in which a body surface of the subject is applied as the information representing the physique of the subject.
  • a form is exemplified in which the specification unit 42 derives an abdominal circumference, a shoulder width, and the like of the subject from the extracted body surface of the subject, and the group in which the subject is classified is specified from the derived physique such as the abdominal circumference, the shoulder width, and the like of the subject.
  • a criterion for metabolic syndrome as a threshold value for specifying a sex, for example.
  • the present invention is not limited thereto.
  • a form may be employed in which the group classified by the sex of the subject is applied, or a form may be employed in which the group classified by the race of the subject is applied.
  • a form may be employed in which the group classified by the species of the subject such as a human, a dog, or a cat is applied.
  • the subject may be classified by a plurality of combinations of the above examples.
  • a form is exemplified in which the subjects are classified in groups classified according to a combination of the age and the sex of the subjects, such as “child/male”, “child/female”, “adult/male”, and “adult/female”.
  • a shape of a central hole in a pelvis is close to a triangle for men and a circle for women. Therefore, it is possible to specify the sex of the subject from the shape of the central hole of the pelvis. In addition, it is possible to specify whether the subject is a human or a non-human from a total number of bones, presence or absence of a tailbone, the number of teeth, and the like.
  • the present invention is not limited thereto.
  • a form may be employed in which the information representing the physique of the subject is extracted from an image captured by a non-medical imaging device.
  • a form is exemplified in which the image analysis processing is performed on the image obtained by imaging the subject with a digital camera to extract the body surface of the subject from the image.
  • a form is exemplified in which a general-purpose learned model 32 common to all groups is prepared in advance and the general-purpose learned model 32 is used in a case where the group in which the subject is classified cannot be specified from the medical image.
  • the various processors include a programmable logic device (PLD) which is a processor whose circuit configuration is changeable after manufacturing such as a field-programmable gate array (FPGA), a dedicated electric circuit which is a processor having a circuit configuration exclusively designed to execute specific processing such as an application specific integrated circuit (ASIC), and the like, in addition to the CPU which is a general-purpose processor that executes software (programs) to function as various processing units as described above.
  • PLD programmable logic device
  • FPGA field-programmable gate array
  • ASIC application specific integrated circuit
  • One processing unit may be configured by one of the various processors or a combination of two or more processors of the same type or different types (for example, a combination of a plurality of FPGAs or a combination of a CPU and an FPGA).
  • a plurality of processing units may be configured by one processor.
  • one processor is configured by a combination of one or more CPUs and software and the processor functions as the plurality of processing units, as represented by computers such as a client and a server.
  • a processor that realizes the functions of the entire system including the plurality of processing units with one integrated circuit (IC) chip is used, as represented by a system-on-chip (SoC) or the like.
  • SoC system-on-chip
  • the various processing units are configured using one or more of the various processors as the hardware structure.
  • circuitry combining circuit elements such as semiconductor elements as the hardware structure of the various processors.
  • the information processing program 30 may be provided in a form of being recorded on a recording medium such as a compact disc read only memory (CD-ROM), a digital versatile disc read only memory (DVD-ROM), and a Universal Serial Bus (USB) memory.
  • the information processing program 30 may be downloaded from an external device through a network.
  • An object of the present disclosure is to provide an information processing device, an information processing method, and a program capable of accurately extracting a target area from a medical image.
  • the information processing device of the present disclosure comprises an extraction unit that extracts information representing a physique of a subject from an image obtained by imaging the subject, a specification unit that specifies a group in which the subject is classified, using the information representing the physique of the subject extracted by the extraction unit, an input unit that inputs image data representing a medical image obtained by imaging the subject to a learned model corresponding to the group specified by the specification unit among learned models obtained in advance for each group by machine learning using learning data for each group, and an acquisition unit that acquires information representing an area extracted from the medical image, which is output from the learned model with the input by the input unit.
  • the information representing the physique of the subject may be a skeleton of the subject.
  • the information representing the physique of the subject may be a body surface of the subject.
  • the image used for extracting the information representing the physique of the subject may be the medical image.
  • the group may be a group in which the subject is classified according to an age, a sex, a race, or a species of the subject.
  • An information processing method executed by a computer comprises extracting information representing a physique of a subject from an image obtained by imaging the subject, specifying a group in which the subject is classified, using the extracted information representing the physique of the subject, inputting image data representing a medical image obtained by imaging the subject to a learned model corresponding to the specified group among learned models obtained in advance for each group by machine learning using learning data for each group, and acquiring information representing an area extracted from the medical image, which is output from the learned model with the input.
  • a non-transitory recording medium of the present disclosure records a program causing a computer to execute the following processing of extracting information representing a physique of a subject from an image obtained by imaging the subject, specifying a group in which the subject is classified, using the extracted information representing the physique of the subject, inputting image data representing a medical image obtained by imaging the subject to a learned model corresponding to the specified group among learned models obtained in advance for each group by machine learning using learning data for each group, and acquiring information representing an area extracted from the medical image, which is output from the learned model with the input.
  • the information processing device of the present disclosure comprises a memory and a processor connected to the memory.
  • the processor is configured to extract information representing a physique of a subject from an image obtained by imaging the subject, specify a group in which the subject is classified by using the extracted information representing the physique of the subject, input image data representing a medical image obtained by imaging the subject to a learned model corresponding to the specified group among learned models obtained for each group by machine learning using learning data for each group, and acquire information representing an area extracted from the medical image, which is output from the learned model with the input.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Data Mining & Analysis (AREA)
  • Veterinary Medicine (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Signal Processing (AREA)
  • Mathematical Physics (AREA)
  • Psychiatry (AREA)
  • Physiology (AREA)
  • General Engineering & Computer Science (AREA)
  • Fuzzy Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Quality & Reliability (AREA)
  • Dentistry (AREA)
US17/241,077 2018-10-29 2021-04-27 Information processing device, information processing method, and program Active 2040-11-10 US11925481B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
JP2018202949 2018-10-29
JP2018-202949 2018-10-29
PCT/JP2019/035852 WO2020090246A1 (ja) 2018-10-29 2019-09-12 情報処理装置、情報処理方法、及びプログラム

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/035852 Continuation WO2020090246A1 (ja) 2018-10-29 2019-09-12 情報処理装置、情報処理方法、及びプログラム

Publications (2)

Publication Number Publication Date
US20210248742A1 US20210248742A1 (en) 2021-08-12
US11925481B2 true US11925481B2 (en) 2024-03-12

Family

ID=70463035

Family Applications (1)

Application Number Title Priority Date Filing Date
US17/241,077 Active 2040-11-10 US11925481B2 (en) 2018-10-29 2021-04-27 Information processing device, information processing method, and program

Country Status (5)

Country Link
US (1) US11925481B2 (ja)
JP (1) JP6968298B2 (ja)
CN (1) CN112970043B (ja)
DE (1) DE112019005378T5 (ja)
WO (1) WO2020090246A1 (ja)

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004267450A (ja) 2003-03-07 2004-09-30 Canon Inc 画像処理装置
JP2006175036A (ja) 2004-12-22 2006-07-06 Fuji Photo Film Co Ltd 肋骨形状推定装置、肋骨形状推定方法およびそのプログラム
JP2007048172A (ja) 2005-08-12 2007-02-22 Fuji Xerox Co Ltd 情報分類装置
JP2007105164A (ja) 2005-10-12 2007-04-26 Hitachi Medical Corp 医用画像診断支援装置
JP2007128127A (ja) 2005-11-01 2007-05-24 Fujifilm Corp 顔検出方法および装置並びにプログラム
JP2009070099A (ja) 2007-09-12 2009-04-02 Ricoh Co Ltd 画像処理装置、画像処理方法、プログラムおよび記録媒体
JP2014023640A (ja) 2012-07-25 2014-02-06 Konica Minolta Inc 画像処理装置及びプログラム
US20140064577A1 (en) 2012-08-29 2014-03-06 Buffalo Inc. Image processing device and recording medium storing program
US20170319150A1 (en) 2016-05-09 2017-11-09 Toshiba Medical Systems Corporation Medical image diagnosis apparatus and management apparatus
US20170323447A1 (en) * 2016-05-09 2017-11-09 Toshiba Medical Systems Corporation Medical image capturing apparatus and method
CN107622281A (zh) 2017-09-20 2018-01-23 广东欧珀移动通信有限公司 图像分类方法、装置、存储介质及移动终端
JP2018134051A (ja) 2017-02-23 2018-08-30 大学共同利用機関法人情報・システム研究機構 情報処理装置、情報処理方法及び情報処理プログラム
US20200118265A1 (en) * 2018-10-10 2020-04-16 Canon Medical Systems Corporation Medical image processing apparatus, medical image processing system, and medical image processing method

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6932554B2 (ja) 2017-05-31 2021-09-08 株式会社シマノ 自転車用ドライブユニット

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004267450A (ja) 2003-03-07 2004-09-30 Canon Inc 画像処理装置
JP2006175036A (ja) 2004-12-22 2006-07-06 Fuji Photo Film Co Ltd 肋骨形状推定装置、肋骨形状推定方法およびそのプログラム
JP2007048172A (ja) 2005-08-12 2007-02-22 Fuji Xerox Co Ltd 情報分類装置
JP2007105164A (ja) 2005-10-12 2007-04-26 Hitachi Medical Corp 医用画像診断支援装置
JP2007128127A (ja) 2005-11-01 2007-05-24 Fujifilm Corp 顔検出方法および装置並びにプログラム
US7809173B2 (en) 2005-11-01 2010-10-05 Fujifilm Corporation Face detection method, apparatus, and program
JP2009070099A (ja) 2007-09-12 2009-04-02 Ricoh Co Ltd 画像処理装置、画像処理方法、プログラムおよび記録媒体
JP2014023640A (ja) 2012-07-25 2014-02-06 Konica Minolta Inc 画像処理装置及びプログラム
US20140064577A1 (en) 2012-08-29 2014-03-06 Buffalo Inc. Image processing device and recording medium storing program
CN103679133A (zh) 2012-08-29 2014-03-26 巴法络股份有限公司 图像处理装置及方法
US20170319150A1 (en) 2016-05-09 2017-11-09 Toshiba Medical Systems Corporation Medical image diagnosis apparatus and management apparatus
US20170323447A1 (en) * 2016-05-09 2017-11-09 Toshiba Medical Systems Corporation Medical image capturing apparatus and method
US11406333B2 (en) * 2016-05-09 2022-08-09 Canon Medical Systems Corporation Medical image diagnosis apparatus and management apparatus
JP2018134051A (ja) 2017-02-23 2018-08-30 大学共同利用機関法人情報・システム研究機構 情報処理装置、情報処理方法及び情報処理プログラム
CN107622281A (zh) 2017-09-20 2018-01-23 广东欧珀移动通信有限公司 图像分类方法、装置、存储介质及移动终端
US20200118265A1 (en) * 2018-10-10 2020-04-16 Canon Medical Systems Corporation Medical image processing apparatus, medical image processing system, and medical image processing method

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"International Search Report (Form PCT/ISA/210) of PCT/JP2019/035852," dated Dec. 10, 2019, with English translation thereof, pp. 1-4.
"Office Action of China Counterpart Application", dated Dec. 23, 2023, with English translation thereof, p. 1-p. 10.
"Written Opinion of the International Searching Authority (Form PCT/ISA/237) of PCT/JP2019/035852," dated Dec. 10, 2019,, with English translation thereof, pp. 1-8.

Also Published As

Publication number Publication date
US20210248742A1 (en) 2021-08-12
JP6968298B2 (ja) 2021-11-17
DE112019005378T5 (de) 2021-07-15
CN112970043B (zh) 2024-05-14
JPWO2020090246A1 (ja) 2021-10-21
CN112970043A (zh) 2021-06-15
WO2020090246A1 (ja) 2020-05-07

Similar Documents

Publication Publication Date Title
US11580642B2 (en) Disease region extraction apparatus, disease region extraction method, and disease region extraction program
US11334990B2 (en) Information processing apparatus, information processing method, and program
US11244455B2 (en) Apparatus, method, and program for training discriminator discriminating disease region, discriminator discriminating disease region, disease region discrimination apparatus, and disease region discrimination program
US20230298759A1 (en) Information processing apparatus, information processing method, and program
US20230005601A1 (en) Document creation support apparatus, method, and program
US20240266056A1 (en) Information processing apparatus, information processing method, and information processing program
JP6843785B2 (ja) 診断支援システム、診断支援方法、及びプログラム
US11769250B2 (en) Medical care support device, medical care support method, and medical care support program
US20230420096A1 (en) Document creation apparatus, document creation method, and document creation program
US11925481B2 (en) Information processing device, information processing method, and program
US11494913B2 (en) Medical care support device, medical care support method, and medical care support program
US11443430B2 (en) Diagnosis support device, diagnosis support method, and diagnosis support program
US20220277448A1 (en) Information processing system, information processing method, and information processing program
US11455728B2 (en) Diagnosis support device, diagnosis support method, and diagnosis support program
US11176413B2 (en) Apparatus, method, and program for training discriminator discriminating disease region, discriminator discriminating disease region, disease region discrimination apparatus, and disease region discrimination program
US11749400B2 (en) Medical care support device, medical care support method, and medical care support program
US20240331335A1 (en) Image processing apparatus, image processing method, and image processing program
US20240037739A1 (en) Image processing apparatus, image processing method, and image processing program
US20240331146A1 (en) Image processing apparatus, image processing method, image processing program, learning apparatus, learning method, and learning program
US20230102745A1 (en) Medical image display apparatus, method, and program
WO2021124869A1 (ja) 診断支援装置、診断支援方法、及び診断支援プログラム
US20240095915A1 (en) Information processing apparatus, information processing method, and information processing program
US20220245925A1 (en) Information processing apparatus, information processing method, and information processing program

Legal Events

Date Code Title Description
FEPP Fee payment procedure

Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

AS Assignment

Owner name: FUJIFILM CORPORATION, JAPAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:YAMADA, KENTA;REEL/FRAME:056134/0589

Effective date: 20210304

STPP Information on status: patent application and granting procedure in general

Free format text: APPLICATION DISPATCHED FROM PREEXAM, NOT YET DOCKETED

STPP Information on status: patent application and granting procedure in general

Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION

STPP Information on status: patent application and granting procedure in general

Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS

STPP Information on status: patent application and granting procedure in general

Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED

STCF Information on status: patent grant

Free format text: PATENTED CASE